Analytic Essay Scoring on ASAP Essay Set 7
0.77Idea QWKFeatEng-RF
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| FeatEng-RFParadigm=Train2026.06 | 0.77 | 0.67 | 0.65 | 0.62 | |
| MADRAGParadigm=Train-free, Model=GPT-52026.06 | 0.75 | 0.63 | 0.47 | 0.19 | |
| MADRAGParadigm=Train-free, Model=GPT-5-mini2026.06 | 0.69 | 0.62 | 0.33 | 0.22 | |
| Human-Human2026.06 | 0.69 | 0.58 | 0.54 | 0.57 | |
| CSR-JParadigm=Train-free, Model=GPT-42026.06 | 0.55 | 0.58 | 0.47 | 0.22 | |
| ProTACTParadigm=Train2026.06 | 0.5 | 0.31 | — | 0.23 | |
| MADRAGParadigm=Train-free, Model=GPT-3.5-turbo2026.06 | 0.45 | 0.34 | 0.24 | 0.16 | |
| MADRAGParadigm=Train-free, Model=GPT-4o-mini2026.06 | 0.43 | 0.64 | 0.47 | 0.26 | |
| MADRAGParadigm=Train-free, Model=GPT-4o2026.06 | 0.4 | 0.38 | 0.35 | 0.28 | |
| ZS-LLMParadigm=Train-free, Model=LLaMA-2-13B-Chat2026.06 | 0.09 | 0.02 | 0.15 | 0.32 | |
| ZS-LLMParadigm=Train-free, Model=GPT-3.5-turbo2026.06 | 0.05 | 0.07 | 0.08 | 0.1 |